Firas Gerges
ABSTRACT
Solar Irradiance depicts the light energy produced by the Sun that hits the Earth. This energy is important for renewable energy generation and is intrinsically fluctuating. Forecasting solar irradiance is crucial for efficient solar energy generation and management. Work in the literature focused on the short-term prediction of solar irradiance, using meteorological data to forecast the irradiance for the next hours, days, or weeks. Facing climate change and the continuous increase of greenhouse gas emissions, particularly from the use of fossil fuels, the reliance on renewable energy sources, such as solar energy, is expanding. Consequently, governments and practitioners are calling for efficient long-term energy generation plans, which could enable 100% renewable-based electricity systems to match energy demand. In this paper, we aim to perform the long-term prediction of solar irradiance, by leveraging the downscaled climate simulations of Global Circulation Models (GCMs). We propose a novel Bayesian deep learning framework, named DeepSI (denoting Deep Solar Irradiance), that employs bidirectional long short-term memory autoencoders, prefixed to a transformer, with an uncertainty quantification component based on the Monte-Carlo dropout sampling technique. We use DeepSI to predict daily solar irradiance for three different locations within the United States. These locations include the Solar Star power station in California, Medford in New Jersey, and Farmers Branch in Texas. Experimental results showcase the suitability of DeepSI for predicting daily solar irradiance from the simulated climate data. We further use DeepSI with future climate simulations to produce long-term projections of daily solar irradiance, up to year 2099.
- F. Wang, Z. Mi, S. Su, and H. Zhao, "Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters", Energies, vol. 5, no. 5, pp. 1355-1370, 2012.Google Scholar
Cross Ref
- K. Y. Bae, H. S. Jang, and D. K. Sung, "Hourly solar irradiance prediction based on support vector machine and its error analysis", IEEE Transactions on Power Systems, vol. 32, no. 2, pp. 935-945, 2016.Google Scholar
- L. Benali, G. Notton, A. Fouilloy, C. Voyant, and R. Dizene, "Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components", Renewable energy, vol. 132, pp. 871-884, 2019.Google ScholarCross Ref
- E. Jumin, F. B. Basaruddin, Y. B. Yusoff, S. D. Latif, and A. N. Ahmed, "Solar radiation prediction using boosted decision tree regression model: A case study in Malaysia", Environmental Science and Pollution Research, vol. 28, no. 21, pp. 26571-26583, 2021.Google ScholarCross Ref
- M. Abuella and B. Chowdhury, "Solar power probabilistic forecasting by using multiple linear regression analysis", in SoutheastCon 2015, 2015: IEEE, pp. 1-5.Google Scholar
- M. Golam, R. Akter, J.-M. Lee, and D.-S. Kim, "A long short-term memory-based solar irradiance prediction scheme using meteorological data", IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2021.Google ScholarCross Ref
- Y. Yu, J. Cao, and J. Zhu, "An LSTM short-term solar irradiance forecasting under complicated weather conditions", IEEE Access, vol. 7, pp. 145651-145666, 2019.Google ScholarCross Ref
- E. Hüllermeier and W. Waegeman, "Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods", Machine Learning, vol. 110, no. 3, pp. 457-506, 2021.Google ScholarCross Ref
- V.-L. Nguyen, S. Destercke, M.-H. Masson, and E. Hüllermeier, "Reliable multi-class classification based on pairwise epistemic and aleatoric uncertainty", in 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), 2018, pp. 5089-5095.Google ScholarDigital Library
- T. Myojin, S. Hashimoto, and N. Ishihama, "Detecting uncertain BNN outputs on FPGA using Monte Carlo dropout sampling", in International Conference on Artificial Neural Networks, 2020: Springer, pp. 27-38.Google ScholarDigital Library
- T. Myojin, S. Hashimoto, K. Mori, K. Sugawara, and N. Ishihama, "Improving reliability of object detection for lunar craters using Monte Carlo dropout", in International Conference on Artificial Neural Networks, 2019: Springer, pp. 68-80.Google ScholarDigital Library
- D. W. Pierce, D. R. Cayan, and B. L. Thrasher, "Statistical downscaling using localized constructed analogs (LOCA)", Journal of Hydrometeorology, vol. 15, no. 6, pp. 2558-2585, 2014.Google ScholarCross Ref
- T. Guo, T. Lin, and N. Antulov-Fantulin, "Exploring interpretable LSTM neural networks over multi-variable data", in 36th International Conference on Machine Learning, 2019: PMLR, pp. 2494-2504.Google Scholar
- I. Segovia-Dominguez, Z. Zhen, R. Wagh, H. Lee, and Y. R. Gel, "TLife-LSTM: forecasting future COVID-19 progression with topological signatures of atmospheric conditions", in 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2021, Cham: Springer, pp. 201-212.Google ScholarDigital Library
- M. Shalaby, J. Stutzki, M. Schubert, and S. Günnemann, "An LSTM approach to patent classification based on fixed hierarchy vectors", in Proceedings of the 2018 SIAM International Conference on Data Mining, 2018: SIAM, pp. 495-503.Google ScholarCross Ref
- A. Graves and N. Jaitly, "Towards end-to-end speech recognition with recurrent neural networks", in International Conference on Machine Learning, 2014: PMLR, pp. 1764-1772.Google Scholar
- S. Zhai, K.-h. Chang, R. Zhang, and Z. M. Zhang, "Deepintent: Learning attentions for online advertising with recurrent neural networks", in Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 1295-1304.Google ScholarDigital Library
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, "Attention is all you need", in Advances in Neural Information Processing Systems, 2017, pp. 5998-6008.Google ScholarDigital Library
- G. Zerveas, S. Jayaraman, D. Patel, A. Bhamidipaty, and C. Eickhoff, "A transformer-based framework for multivariate time series representation learning", in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 2114-2124.Google ScholarDigital Library
- D. Martín-Gutiérrez, G. Hernández-Peñaloza, A. B. Hernández, A. Lozano-Diez, and F. Álvarez, "A deep learning approach for robust detection of bots in twitter using transformers", IEEE Access, vol. 9, pp. 54591-54601, 2021.Google ScholarCross Ref
- P. Saltz, S. Y. Lin, S. C. Cheng, and D. Si, "Dementia detection using transformer-based deep learning and natural language processing models", in 2021 IEEE 9th International Conference on Healthcare Informatics (ICHI), 2021: IEEE, pp. 509-510.Google Scholar
- K. Ikromjanov, S. Bhattacharjee, Y.-B. Hwang, R. I. Sumon, H.-C. Kim, and H.-K. Choi, "Whole slide image analysis and detection of prostate cancer using vision transformers", in 2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 2022: IEEE, pp. 399-402.Google Scholar
- L. Shen and Y. Wang, "TCCT: tightly-coupled convolutional transformer on time series forecasting", Neurocomputing, 2022.Google Scholar
- A. Narayan, B. S. Mishra, P. S. Hiremath, N. T. Pendari, and S. Gangisetty, "An Ensemble of transformer and LSTM approach for multivariate time series data classification", in 2021 IEEE International Conference on Big Data (Big Data), 2021: IEEE, pp. 5774-5779.Google Scholar
- K. Zhang, C. Hawkins, and Z. Zhang, "General-purpose Bayesian tensor learning with automatic rank determination and uncertainty quantification", Frontiers in Artificial Intelligence, vol. 4, 2021.Google Scholar
- J. Liu, "Variable selection with rigorous uncertainty quantification using deep Bayesian neural networks: Posterior concentration and Bernstein-von Mises phenomenon", in International Conference on Artificial Intelligence and Statistics, 2021: PMLR, pp. 3124-3132.Google Scholar
- Y. Wang and V. Rocková, "Uncertainty quantification for sparse deep learning", in International Conference on Artificial Intelligence and Statistics, 2020: PMLR, pp. 298-308.Google Scholar
- Y. Kwon, J.-H. Won, B. J. Kim, and M. C. Paik, "Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation", Computational Statistics & Data Analysis, vol. 142, p. 106816, 2020.Google ScholarDigital Library
- H. Jiang, J. Jing, J. Wang, C. Liu, Q. Li, Y. Xu, J. T. L. Wang, and H. Wang, "Tracing Hα fibrils through Bayesian deep learning", The Astrophysical Journal Supplement Series, vol. 256, no. 1, p. 20, 2021.Google ScholarCross Ref
- D. M. Blei, A. Kucukelbir, and J. D. McAuliffe, "Variational inference: A review for statisticians", Journal of the American statistical Association, vol. 112, no. 518, pp. 859-877, 2017.Google ScholarCross Ref
Index Terms
- Deep Learning-Enabled Prediction of Daily Solar Irradiance from Simulated Climate Data
Recommendations
Long-term prediction of daily solar irradiance using Bayesian deep learning and climate simulation data
AbstractSolar Irradiance depicts the light energy produced by the Sun that hits the Earth. This energy is important for renewable energy generation and is intrinsically fluctuating. Forecasting solar irradiance is crucial for efficient solar energy ...
A 24h forecast of solar irradiance using echo state neural networks
EANN '15: Proceedings of the 16th International Conference on Engineering Applications of Neural Networks (INNS)Artificial neural networks have demonstrated to be good at timeseries forecasting problems, being widely studied in literature. In this study an artificial neural network model is introduced for modelling the solar irradiance. Forecasting of solar ...
Short-term solar irradiance forecasting in streaming with deep learning
Highlights- Accurate solar irradiance forecasting with deep learning (DL) in an online learning scenario.
AbstractSolar energy is one of the most common and promising sources of renewable energy. In photovoltaic (PV) systems, operators can benefit from future solar irradiance predictions for efficient load balancing and grid stability. Therefore, ...
Comments